International Conference on Machine Learning, Artificial Intelligence and Data Science

Salah HAMMEDI Profile

Salah HAMMEDI

Salah HAMMEDI

Biography

Salah Hammedi is a researcher and lecturer in Computer Science, currently affiliated with the Higher Institute of Applied Mathematics and Computer Science of Kairouan (ISMAI-K), University of Kairouan, Tunisia. He holds a Ph.D. in Electrical Engineering from the National Engineering School of Monastir (ENIM), awarded in 2025, where his doctoral work focused on the optimization of production systems through intelligent algorithms, particularly Petri Nets and Artificial Intelligence (AI) techniques. He also earned a Master?s degree in Intelligent Information Systems from ISIGK, with earlier research centered on driver assistance technologies. Dr. Hammedi is an active member of the Networked Objects Control and Communication Systems Laboratory (NOCCS) at the University of Sousse. His primary research interests include smart manufacturing, AI-driven optimization, meta-heuristics, dynamic task allocation, and reconfigurable production systems. His contributions have been published in 7 international journals and presented at 3 major international conferences, addressing topics such as production scheduling, genetic algorithms, Petri net modeling, and real-time object tracking using YOLOv5. He is also a reviewer for several peer-reviewed journals and serves as an Academic Board Member for Global Open Share Publishing (GOSP).

Research Interest

Artificial Intelligence ? Optimization ? Meta-heuristics ? Intelligent Systems ? Scheduling ? Manufacturing

Abstract

AI-Driven Product Personalization in RMS using Generative Models We present an AI-based personalization framework using Generative Adversarial Networks (GANs) to configure product designs and manufacturing processes in RMS. The GAN generates optimized product parameters and process settings based on customer input. Tested on a flexible electronics production line, our method increases customer satisfaction scores by 24% and reduces customization lead time by 37% compared to manual configuration. The proposed system enhances agility and responsiveness, making AI-driven personalization feasible in reconfigurable industrial settings